Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation

Bendimered, Abderrahmen; Iguernaissi, Rabah; Nawaf, Mohamad Motasem; Cherif, Rim; Dubuisson, Séverine; Merad, Djamal

doi:10.3390/s25134086

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation

by

Abderrahmen Bendimered

^*

,

Rabah Iguernaissi

,

Mohamad Motasem Nawaf

,

Rim Cherif

,

Séverine Dubuisson

and

Djamal Merad

Laboratoire d’Informatique et des Systèmes, CNRS UMR 7020, Aix-Marseille University, 13009 Marseille, France

^*

Author to whom correspondence should be addressed.

Sensors 2025, 25(13), 4086; https://doi.org/10.3390/s25134086

Submission received: 14 May 2025 / Revised: 23 June 2025 / Accepted: 26 June 2025 / Published: 30 June 2025

(This article belongs to the Special Issue Advances in Optical Sensing, Instrumentation and Systems: 2nd Edition)

Download Versions Notes

Abstract

Estimating gaze direction is a key task in computer vision, especially for understanding where a person is focusing their attention. It is essential for applications in assistive technology, medical diagnostics, virtual environments, and human–computer interaction. In this work, we introduce Dual Focus-3D, a novel hybrid deep learning architecture that combines appearance-based features from eye images with 3D head orientation data. This fusion enhances the model’s prediction accuracy and robustness, particularly in challenging natural environments. To support training and evaluation, we present EyeLis, a new dataset containing 5206 annotated samples with corresponding 3D gaze and head pose information. Our model achieves state-of-the-art performance, with a MAE of 1.64° on EyeLis, demonstrating its ability to generalize effectively across both synthetic and real datasets. Key innovations include a multimodal feature fusion strategy, an angular loss function optimized for 3D gaze prediction, and regularization techniques to mitigate overfitting. Our results show that including 3D spatial information directly in the learning process significantly improves accuracy.

Keywords: 3D Gaze Estimation; computer vision; multimodal fusion; EyeLis dataset

Share and Cite

MDPI and ACS Style

Bendimered, A.; Iguernaissi, R.; Nawaf, M.M.; Cherif, R.; Dubuisson, S.; Merad, D. Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation. Sensors 2025, 25, 4086. https://doi.org/10.3390/s25134086

AMA Style

Bendimered A, Iguernaissi R, Nawaf MM, Cherif R, Dubuisson S, Merad D. Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation. Sensors. 2025; 25(13):4086. https://doi.org/10.3390/s25134086

Chicago/Turabian Style

Bendimered, Abderrahmen, Rabah Iguernaissi, Mohamad Motasem Nawaf, Rim Cherif, Séverine Dubuisson, and Djamal Merad. 2025. "Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation" Sensors 25, no. 13: 4086. https://doi.org/10.3390/s25134086

APA Style

Bendimered, A., Iguernaissi, R., Nawaf, M. M., Cherif, R., Dubuisson, S., & Merad, D. (2025). Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation. Sensors, 25(13), 4086. https://doi.org/10.3390/s25134086

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Dual Focus-3D: A Hybrid Deep Learning Approach for Robust 3D Gaze Estimation

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI